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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 47998
    Prev
    Next
    INDEX
    Explanations

    star

    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
    程度
    -0.09
     واري
    -0.08
     condoms
    -0.08
     videot
    -0.07
     Clique
    -0.07
     Thur
    -0.07
     recuer
    -0.07
    ավորվ
    -0.07
     paranoia
    -0.07
    CL
    -0.07
    POSITIVE LOGITS
    들에게
    0.09
    에게
    0.08
     nursery
    0.08
     residence
    0.08
    505
    0.08
     emitted
    0.08
     Emits
    0.08
     신
    0.08
     emits
    0.08
     Jou
    0.08
    Activations Density 0.005%

    No Known Activations