© 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. 7-RESID-POST-AA
    11. 1486
    Prev
    Next
    INDEX
    Explanations

    foreign languages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Mall
    -0.08
    Seguro
    -0.08
    Insn
    -0.08
    Nut
    -0.08
    Else
    -0.08
     else
    -0.08
     بسی
    -0.08
    ++,
    -0.08
    ूँ
    -0.07
    тердің
    -0.07
    POSITIVE LOGITS
     Inject
    0.08
    isd
    0.08
     Bloomberg
    0.08
     bok
    0.07
     सूर्य
    0.07
     bol
    0.07
     Sun
    0.07
    opup
    0.07
     �
    0.07
     capita
    0.07
    Activations Density 0.000%

    No Known Activations