© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 7-RESID-POST-AA
    6. 1311
    Prev
    Next
    INDEX
    Explanations

    RPG features and feats

    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
     ema
    -0.09
     ATR
    -0.08
     Armen
    -0.08
     Fender
    -0.08
     Brady
    -0.08
     immer
    -0.08
     impedance
    -0.08
    Synth
    -0.08
     Nile
    -0.07
     pè
    -0.07
    POSITIVE LOGITS
    går
    0.08
     talentos
    0.08
     Cloud
    0.08
     ಮಾತ
    0.08
    Cloud
    0.08
     CLOUD
    0.07
    검
    0.07
     korting
    0.07
     talents
    0.07
     realloc
    0.07
    Activations Density 0.005%

    No Known Activations