© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 114148
    Prev
    Next
    INDEX
    Explanations

    math problems/solutions

    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
     evidenced
    -0.07
    -0.07
    jenje
    -0.07
     victory
    -0.07
     enemies
    -0.07
     evidence
    -0.06
     Um
    -0.06
     كلا
    -0.06
     enemy
    -0.06
     Dois
    -0.06
    POSITIVE LOGITS
     reka
    0.09
    =t
    0.08
    .tight
    0.08
    _subject
    0.08
     hingegen
    0.08
     tese
    0.08
     пән
    0.08
     stan
    0.08
     vaka
    0.08
     букмекер
    0.08
    Activations Density 0.186%
    No Known Activations