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. 119357
    Prev
    Next
    INDEX
    Explanations

    or

    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
    :"↵
    -0.08
     Latino
    -0.08
    ത്
    -0.08
    ൾ
    -0.08
     requester
    -0.08
     Rok
    -0.07
     naro
    -0.07
    -party
    -0.07
    -assisted
    -0.07
     Emergency
    -0.07
    POSITIVE LOGITS
     stuff
    0.10
    とか
    0.08
     forth
    0.08
    whatever
    0.08
     stuffs
    0.08
    VX
    0.08
     yada
    0.08
    something
    0.08
    या
    0.08
    VIOUS
    0.08
    Activations Density 0.091%

    No Known Activations