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. 65187
    Prev
    Next
    INDEX
    Explanations

    transcendental equations

    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
    ilerin
    -0.09
    ികളുടെ
    -0.08
     Ausland
    -0.08
    ünftig
    -0.08
     poverty
    -0.08
     favorit
    -0.08
     wear
    -0.08
     Zuschauer
    -0.08
    _actions
    -0.08
     забот
    -0.08
    POSITIVE LOGITS
     transcend
    0.09
     ln
    0.08
     computador
    0.08
     Ln
    0.08
    -ln
    0.07
     sigmoid
    0.07
     nv
    0.07
     콘
    0.07
     nuk
    0.07
     eval
    0.07
    Activations Density 0.037%

    No Known Activations