© 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. 129303
    Prev
    Next
    INDEX
    Explanations

    of

    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
    -cr
    -0.08
    fad
    -0.08
     interpr
    -0.07
     midfield
    -0.07
     pity
    -0.07
     issuer
    -0.07
     Fle
    -0.07
     Uf
    -0.07
     Samm
    -0.07
    Pf
    -0.07
    POSITIVE LOGITS
     എന്നിവ
    0.09
     എന്നിവർ
    0.08
     וכו
    0.08
     ஆகிய
    0.08
     และ
    0.08
    alala
    0.08
    以及
    0.08
     ved
    0.07
    ，以及
    0.07
    れる
    0.07
    Activations Density 0.161%

    No Known Activations