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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 75981
    Prev
    Next
    INDEX
    Explanations

    logical statements

    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
    COPY
    -0.08
    kop
    -0.08
     ditch
    -0.08
    abras
    -0.08
     Kop
    -0.08
    พัก
    -0.07
    Cube
    -0.07
    Tips
    -0.07
     Ruhe
    -0.07
    spedes
    -0.07
    POSITIVE LOGITS
    真假
    0.10
     truthful
    0.10
     truth
    0.10
     Truth
    0.10
     liar
    0.09
     सत्य
    0.09
    Truth
    0.09
     doğr
    0.09
    _truth
    0.09
     Conce
    0.08
    Activations Density 0.016%

    No Known Activations