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. 120178
    Prev
    Next
    INDEX
    Explanations

    x

    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
     claimed
    -0.08
     claims
    -0.08
     seksuele
    -0.08
    毛
    -0.08
    宣传
    -0.08
    済
    -0.08
     inactive
    -0.08
     partners
    -0.07
     Couples
    -0.07
    partners
    -0.07
    POSITIVE LOGITS
    :G
    0.08
     journey
    0.08
     속
    0.08
    127
    0.07
    ^
    0.07
    _squared
    0.07
    xbf
    0.07
    .exports
    0.07
    ;q
    0.07
    Squared
    0.07
    Activations Density 0.038%

    No Known Activations