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. 54193
    Prev
    Next
    INDEX
    Explanations

    Comparisons

    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
    Ob
    -0.09
    .Ad
    -0.09
    Ad
    -0.08
     Obl
    -0.07
     Ad
    -0.07
    Cm
    -0.07
     correspon
    -0.07
    .member
    -0.07
    [Serialize
    -0.07
    struction
    -0.07
    POSITIVE LOGITS
     ():
    0.11
     yaitu
    0.08
    ,就是
    0.08
    ){//
    0.08
    つまり
    0.08
     embrace
    0.08
    】:
    0.08
     детьми
    0.08
    (){↵//
    0.08
    一样
    0.08
    Activations Density 0.036%

    No Known Activations