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. 27691
    Prev
    Next
    INDEX
    Explanations

    un

    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
     Gandhi
    -0.08
    	source
    -0.08
    _FIL
    -0.08
     unconscious
    -0.08
     entreprene
    -0.08
     subconscious
    -0.08
    γνω
    -0.08
    ười
    -0.07
     source
    -0.07
    source
    -0.07
    POSITIVE LOGITS
    라
    0.08
     Pis
    0.08
    Inv
    0.08
    드
    0.07
    ણી
    0.07
    rops
    0.07
    ынды
    0.07
    _buffers
    0.07
    .toast
    0.07
    ward
    0.07
    Activations Density 0.000%

    No Known Activations