© 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. 48008
    Prev
    Next
    INDEX
    Explanations

    "already" and pre-existing states

    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
    ek
    -0.09
    eb
    -0.08
     miš
    -0.08
    Ess
    -0.08
     viewpoint
    -0.07
    (background
    -0.07
     illegally
    -0.07
     perspectives
    -0.07
    ez
    -0.07
    eras
    -0.07
    POSITIVE LOGITS
     straightforward
    0.13
     그대로
    0.13
    直接
    0.12
     langsung
    0.12
     सीधे
    0.11
     સી
    0.11
     diretamente
    0.10
     directamente
    0.10
     doğ
    0.10
     direto
    0.10
    Activations Density 0.082%

    No Known Activations