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. 30775
    Prev
    Next
    INDEX
    Explanations

    states

    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
    zur
    -0.09
     მ
    -0.08
     geometry
    -0.08
    ffset
    -0.08
    elm
    -0.07
    PG
    -0.07
    gm
    -0.07
    .Move
    -0.07
    geometry
    -0.07
     pleasant
    -0.07
    POSITIVE LOGITS
     Children
    0.09
     नियम
    0.08
     "**
    0.08
    ब
    0.08
     ríg
    0.08
     Kathleen
    0.08
     '**
    0.08
     infatti
    0.08
     bikini
    0.07
     kiddos
    0.07
    Activations Density 0.012%

    No Known Activations