© 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. 68128
    Prev
    Next
    INDEX
    Explanations

    confession

    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
     flop
    -0.07
     fry
    -0.07
     Debbie
    -0.07
     shareholder
    -0.07
     propagation
    -0.07
     voorsp
    -0.07
     kokos
    -0.07
     feit
    -0.07
     promoters
    -0.07
     δεί
    -0.07
    POSITIVE LOGITS
     sins
    0.10
     apparatus
    0.09
    enticator
    0.09
     circonst
    0.09
     ರೂಪ
    0.08
     anguish
    0.08
     discharge
    0.08
    Contra
    0.08
     Worten
    0.08
    ipsoid
    0.07
    Activations Density 0.004%

    No Known Activations