Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 61044
    Prev
    Next
    INDEX
    Explanations

    FHIR

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     oby
    -0.09
    alty
    -0.08
    iw
    -0.07
     enquiry
    -0.07
    Charles
    -0.07
    Poly
    -0.07
    rey
    -0.07
    Def
    -0.07
    ued
    -0.07
    裏
    -0.07
    POSITIVE LOGITS
    helf
    0.09
    ograma
    0.09
    versorgung
    0.08
     residential
    0.08
     ritmo
    0.08
     outpatient
    0.08
     bela
    0.08
     inser
    0.08
    telefone
    0.07
     preciosa
    0.07
    Activations Density 0.002%

    No Known Activations