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. 65304
    Prev
    Next
    INDEX
    Explanations

    full

    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
     Rab
    -0.09
     overwritten
    -0.08
    Rab
    -0.08
     Afro
    -0.08
    faz
    -0.07
     svarte
    -0.07
    Bush
    -0.07
    _dirty
    -0.07
    anity
    -0.07
    oppen
    -0.07
    POSITIVE LOGITS
    -scale
    0.09
    -spectrum
    0.09
    तः
    0.08
    ssid
    0.08
     Hodg
    0.08
     workload
    0.08
    0.08
     ọrụ
    0.07
    zeitig
    0.07
    Patrick
    0.07
    Activations Density 0.026%

    No Known Activations