© 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. 23-RESID-POST-AA
    11. 48124
    Prev
    Next
    INDEX
    Explanations

    B

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OY
    -0.11
    Nl
    -0.11
    ұл
    -0.10
    Rl
    -0.10
    CX
    -0.10
    DDS
    -0.10
    CJ
    -0.10
    O
    -0.10
    CQ
    -0.10
    CZ
    -0.09
    POSITIVE LOGITS
    ovendien
    0.13
    linni
    0.13
    orghini
    0.12
    angalore
    0.11
    ournemouth
    0.11
    eteilig
    0.10
    íodh
    0.10
    unifu
    0.10
    accarat
    0.10
    airro
    0.10
    Activations Density 0.056%

    No Known Activations