Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 61097
    Prev
    Next
    INDEX
    Explanations

    signatures

    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
     kommer
    -0.08
     Somit
    -0.08
    ระดับ
    -0.08
    τικό
    -0.07
    Parad
    -0.07
     verbindet
    -0.07
    nty
    -0.07
     episod
    -0.07
    ntl
    -0.07
     شدن
    -0.07
    POSITIVE LOGITS
    ев
    0.08
    /thumb
    0.08
     gov
    0.07
     �
    0.07
     配
    0.07
    栏
    0.07
    @Getter
    0.07
    养
    0.07
     �
    0.07
     wła
    0.07
    Activations Density 0.003%

    No Known Activations