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. 61085
    Prev
    Next
    INDEX
    Explanations

    floor

    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
     interpolation
    -0.08
     interpolate
    -0.08
    .win
    -0.07
     declare
    -0.07
    Wins
    -0.07
     wins
    -0.07
    962
    -0.07
     phải
    -0.07
    Interpolation
    -0.07
    explicit
    -0.07
    POSITIVE LOGITS
     pastime
    0.10
     mør
    0.09
    闲
    0.09
     günd
    0.09
     downstairs
    0.09
     niches
    0.09
     darkness
    0.09
    下来
    0.08
     gezellig
    0.08
     Down
    0.08
    Activations Density 0.026%

    No Known Activations