© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 23-RESID-POST-AA
    11. 47879
    Prev
    Next
    INDEX
    Explanations

    Describing a person's character

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ичество
    -0.09
     viscosity
    -0.09
     potency
    -0.08
     vitality
    -0.08
     supremacy
    -0.08
     Lieferung
    -0.08
     Geschwindigkeit
    -0.08
     toxicity
    -0.08
    izlik
    -0.08
     गति
    -0.08
    POSITIVE LOGITS
     patient
    0.20
     enthusi
    0.18
     diligent
    0.17
    Patient
    0.17
     courteous
    0.17
    patient
    0.17
     hardworking
    0.16
     observ
    0.15
     curious
    0.15
     personable
    0.15
    Activations Density 0.083%

    No Known Activations