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. 60493
    Prev
    Next
    INDEX
    Explanations

    Hormones

    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
     peace
    -0.08
     rhyme
    -0.08
     Android
    -0.08
     parecido
    -0.08
    /build
    -0.08
     butcher
    -0.08
     mécanique
    -0.08
    .gradle
    -0.07
    �
    -0.07
     arquivos
    -0.07
    POSITIVE LOGITS
     precursor
    0.09
    _INPUT
    0.08
     PY
    0.08
     док
    0.08
     synerg
    0.08
     pyl
    0.08
    _CODES
    0.08
    _CM
    0.08
     Send
    0.08
     hvad
    0.07
    Activations Density 0.005%

    No Known Activations