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. 65877
    Prev
    Next
    INDEX
    Explanations

    axis

    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
     salir
    -0.08
    Alert
    -0.08
     acute
    -0.08
    ubb
    -0.07
     outsourced
    -0.07
     Alert
    -0.07
    -0.07
     holistic
    -0.07
     ruimte
    -0.07
     elevated
    -0.07
    POSITIVE LOGITS
    轴
    0.08
     squeez
    0.08
     Orth
    0.08
    يض
    0.08
     reyn
    0.08
    જય
    0.08
    -axis
    0.08
    _extent
    0.08
     Marbella
    0.08
     DEM
    0.08
    Activations Density 0.009%

    No Known Activations