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. 129934
    Prev
    Next
    INDEX
    Explanations

    species

    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
     betr
    -0.08
     betray
    -0.07
     conject
    -0.07
    /back
    -0.07
    ban
    -0.07
     Jubilee
    -0.07
    խ
    -0.07
    sequ
    -0.07
     кабин
    -0.07
    êtes
    -0.07
    POSITIVE LOGITS
    -specific
    0.09
     pul
    0.08
    wide
    0.08
     orig
    0.08
     pup
    0.08
    별
    0.08
     madre
    0.08
    _descriptor
    0.07
    Mol
    0.07
    级
    0.07
    Activations Density 0.007%

    No Known Activations