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. 15-RESID-POST-AA
    6. 18930
    Prev
    Next
    INDEX
    Explanations

    code and physics

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    POPULAR
    -0.10
    Tou
    -0.09
    Qualified
    -0.08
     Rég
    -0.08
     maður
    -0.08
    ITERAL
    -0.08
    STA
    -0.08
     rú
    -0.08
     eý
    -0.08
     INST
    -0.08
    POSITIVE LOGITS
    :
    0.09
     and
    0.09
     Ca
    0.08
    /cm
    0.08
     nicht
    0.07
    anei
    0.07
    _ke
    0.07
    :{↵
    0.07
     ikke
    0.07
    **
    0.07
    Activations Density 0.000%

    No Known Activations