© 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. 75517
    Prev
    Next
    INDEX
    Explanations

    a

    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
    chooser
    -0.08
     औ
    -0.08
    sharp
    -0.07
     stvar
    -0.07
     amplio
    -0.07
     ఉంటుంది
    -0.07
     सके
    -0.07
    ADF
    -0.07
    quilo
    -0.07
     prepre
    -0.07
    POSITIVE LOGITS
    偶
    0.10
     antique
    0.09
    Reading
    0.08
     unexpectedly
    0.08
    ，却
    0.08
     negligence
    0.08
     innoc
    0.08
    রত
    0.08
     unconscious
    0.08
     surprisingly
    0.08
    Activations Density 0.057%

    No Known Activations