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. 112287
    Prev
    Next
    INDEX
    Explanations

    Mammoths

    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
     sonra
    -0.07
    andan
    -0.07
    uyor
    -0.07
    adius
    -0.07
     ई
    -0.07
    -songwriter
    -0.07
    pg
    -0.07
     mangel
    -0.07
     eq
    -0.07
     YC
    -0.07
    POSITIVE LOGITS
    Frozen
    0.08
    Loads
    0.08
    _REV
    0.08
     Dud
    0.08
     funer
    0.08
    0.07
     Frozen
    0.07
    ුණ
    0.07
    -lasting
    0.07
    _ru
    0.07
    Activations Density 0.001%

    No Known Activations