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. 12207
    Prev
    Next
    INDEX
    Explanations

    }

    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
     тем
    -0.08
     youtube
    -0.07
     GTX
    -0.07
     Raceway
    -0.07
    .each
    -0.07
     populaire
    -0.07
     HMS
    -0.07
     GPL
    -0.07
     license
    -0.07
     thrill
    -0.07
    POSITIVE LOGITS
    (single
    0.11
    singleton
    0.10
    -single
    0.10
    single
    0.10
     Singleton
    0.10
    .single
    0.10
    單
    0.10
    .Single
    0.09
    .singleton
    0.09
    _single
    0.09
    Activations Density 0.014%

    No Known Activations