© 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. 47556
    Prev
    Next
    INDEX
    Explanations

    Gr or gr

    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
     dafür
    -0.08
    ensity
    -0.07
     escalate
    -0.07
     v
    -0.07
     गंभीर
    -0.07
     ambul
    -0.07
     east
    -0.06
     Plaza
    -0.06
     June
    -0.06
     meter
    -0.06
    POSITIVE LOGITS
    aba
    0.09
    ábh
    0.09
    Families
    0.09
    ավար
    0.09
     মতো
    0.08
    anın
    0.08
    ابه
    0.08
    ախոս
    0.08
     Seb
    0.08
    uffled
    0.08
    Activations Density 0.000%

    No Known Activations