© 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. 216
    Prev
    Next
    INDEX
    Explanations

    letters and strings

    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
    fford
    -0.08
     অভিযোগ
    -0.08
     विवाद
    -0.08
    criptions
    -0.08
     قضية
    -0.08
    Composable
    -0.07
     renovations
    -0.07
    quent
    -0.07
    Modern
    -0.07
     Bought
    -0.07
    POSITIVE LOGITS
     uppercase
    0.15
    uppercase
    0.14
     lowercase
    0.14
     letters
    0.13
    letters
    0.12
    _letters
    0.12
     Letters
    0.10
     lettere
    0.10
     бук
    0.10
    Letters
    0.10
    Activations Density 0.007%

    No Known Activations